arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.09342eess.SP
收藏

一种结合视频数据的跨模态预训练框架,用于提升分布式声学传感的性能与泛化能力

A cross-modal pre-training framework with video data for improving performance and generalization of distributed acoustic sensing

Junyi Duan, Jiageng Chen, Zuyuan He

AI总结:

针对DAS-MAE在频率分析和数据需求上的局限性,提出结合STFT时频特征提取与视频到DAS跨模态预训练的框架,大幅提升少样本分类及损伤预防任务性能,扩展训练资源并推动工业IoT传感跨模态学习。

摘要:

光纤分布式声学传感(DAS)已成为关键的物联网(IoT)传感技术,具有广泛的工业应用。然而,DAS信号的二维时空形态带来了分析挑战,传统方法表现欠佳,而深度学习方法则更适合此类任务。尽管我们之前的工作——DAS掩码自动编码器(DAS-MAE)在无标签情况下实现了最先进的性能和泛化能力,但在以时间为主导的DAS数据的频率分析方面仍不令人满意。此外,有效训练数据的局限性无法满足DAS-MAE中Transformer架构固有的大量数据需求。为克服这些局限性,我们提出了一种增强框架,该框架结合短时傅里叶变换(STFT)以进行显式的时频特征提取,并开创性地采用视频到DAS的跨模态预训练来缓解数据约束。该方法通过无标签重构任务学习高级表示(例如事件分类)。实验结果显示出显著改进:少样本分类的错误率为0.1%(相对DAS-MAE提升90.9%),外部损伤预防应用中的识别错误率为4.7%(相对从头训练提升75.4%)。作为首个开创视频到DAS跨模态预训练的工作,该框架通过连接计算机视觉和分布式传感领域扩展了可用训练资源。增强的性能和泛化能力促进了DAS在各种工业场景中的部署,同时推动了工业物联网传感的跨模态表示学习。

英文摘要:

Fiber-optic distributed acoustic sensing (DAS) has emerged as a critical Internet-of-Things (IoT) sensing technology with broad industrial applications. However, the two-dimensional spatial-temporal morphology of DAS signals presents analytical challenges where conventional methods prove suboptimal, while being well-suited for deep learning approaches. Although our previous work, DAS Masked Autoencoder (DAS-MAE), established state-of-the-art performance and generalization without labels, it is not satisfactory in frequency analysis in temporal-dominated DAS data. Moreover, the limitation of effective training data fails to address the substantial data requirements inherent to Transformer architectures in DAS-MAE. To overcome these limitations, we present an enhanced framework incorporating short-time Fourier transform (STFT) for explicit temporal-frequency feature extraction and pioneering video-to-DAS cross-modal pre-training to mitigate data constraints. This approach learns high-level representations (e.g., event classification) through label-free reconstruction tasks. Experimental results demonstrate transformative improvements: 0.1% error rate in few-shot classification (90.9% relative improvement over DAS-MAE) and 4.7% recognition error in external damage prevention applications (75.4% improvement over from-scratch training). As the first work to pioneer video-to-DAS cross-modal pre-training, available training resources are expanded by bridging computer vision and distributed sensing areas. The enhanced performance and generalization facilitate DAS deployment across diverse industrial scenarios while advancing cross-modal representation learning for industrial IoT sensing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑